They even doesn't do somewhat decent with Intel up the higher tier....
I remember the old times when Intel CPU was shipped with a decent nVIDIA or AMD dGPU.... sadly, seems that those times won't come back....
"Utimate crap" is admittedly a perjurotive term, but all you have to do is look at marketshare in the server market to see the facts. In the bulldozer era, AMDs share went from i think around 20% to around 5%. And you are trying to defend this product?
Mate, I'm not here to argue with you. My post was to illuminate how extreme the bias is in some posts around here. There are posts full of ludicrous statements and unsubstantiated claims, and they're made by posters who will troll threads "arguing" with anyone who disagrees.
In the bulldozer era, AMDs share went from i think around 20% to around 5%. And you are trying to defend this product?
To explain this we might also call the human factor. This is not only a problem in forums and among sports fans. This also plays a role in companies. And I've learned many interesting things about it's influence. Most of us are no rational machines. That's why marketing ppl or company leaders might hide the complete truth. This happens and it surely wasn't Lisa Su's or Jim Keller's fault.
And I propose following hypothesis: This decline has by a large part been caused by Intel's continuously improved offerings while AMD didn't do much there. The rest can be explained by lowered prices, FMA advantages in the beginning, later lost focus in server/HPC business (aside from SeaMicro) and probably some other points like JF leaving AMD.
Oh, I was referring to the lowest tier. I had a Intel Pentium P6000 CPU (upgraded to Core i3 380M, much better than any Core i3 U tier Haswell) with an AMD HD 5470 dGPU. I was meant to post, sorry I am forgot that little detail D:There are plenty of laptops with intel cpus and nvidia dgpus. In fact I just bought my grandson a nice asus gaming laptop with an intel i7 and a GTX960M for his graduation gift.
As for AMD, performance per watt of their dgpus is not competitive with Maxwell and optimus gpu switching has always been much better implemented than enduro or whatever AMD call their system. Thus their lack of presence in laptops.
And I propose following hypothesis: This decline has by a large part been caused by Intel's continuously improved offerings while AMD didn't do much there. The rest can be explained by lowered prices, FMA advantages in the beginning, later lost focus in server/HPC business (aside from SeaMicro) and probably some other points like JF leaving AMD.
There is nothing unsubstantiated in calling all AMD current AMD chips a crap on the server market.
There is a difference between painting your product in the most positive light possible and painting your product in a manner completely divorced from reality. Unfortunately AMD leans towards the latter. Take for example the server market, Bulldozer was the ultimate crap on that market, even if processors came for free it wouldn't make sense to build a Bulldozer server, but yet the company failed to acknowledge this and tried to push that dog on the server market. The result was that not only the company server business was wiped out, AMD credibility on that market also was severely damaged.
So AMD leans towards being "divorced from reality"? I knew engineers were a queer folk.
And Bulldozer was "the ultimate crap" on the server market? I think I need a definition...
In fact you claim "even if processors came for free it wouldn't make sense to build a Bulldozer server". And you even try to blame AMD for not acknowledging this? Lulz. I would love to see your numbers.
And you go on to claim [AMD's] "server business was wiped out". Of which your proof is something other than the ongoing server development.
If something was going to be described as "the ultimate crap" on anything... I'm surprised at the level of well thought out, objective, technical, & substantiated discussion going on.
Did amd announce a Carrizo server chip?
Not that I know of. I've heard noise about Excavator/Carrizo only supporting DDR4 for "server parts", but I'll be darned if I know what are those parts.
Did amd announce a Carrizo server chip?
LOL. Are you serious?and probably some other points like JF leaving AMD
It could've been the other way round. They had the plan for another server processor from the beginning. That's as business is expected to happen if it is full of MBAs. The R&D teams and engineers have to deliver. But with such complex things as CPUs where you've still to find the solutions, which are already scheduled and tied to milestones, there could always be delays, buggy features, wrong assumptions (heuristics), imprecise simulations, etc. This is the human factor at work at every level.When I say incompetent I think I'm already implying human factors. AMD management in general is very incompetent. That they tried to portrait something like Bulldozer as a server processor is just the icing on the cake. They didn't hide the complete truth, they screwed up big time in the marketing message.
When did they flush the entire pipeline? They left out finishing some projects like Krishna, Wichita, Skybridge, and others, which was either related to GF processes, market situations or changed plans. The last big µarch thing being cancelled which I know of is David Christie's (and even Jim Keller's) original K8 design. Nothing is really missing in the construction line. Ok, the only thing I might miss from the original µarch roadmap is "greater parallelism" of SR, but this is interpretation (in the end +0.1% is "greater"). Other topics like ASF have been developed, but didn't get a go - possibly due to discontinueing the server line. Otherwise they'd have announced it, since ASF is nothing else than TSX.The decline was not because AMD didn't do much, but because they failed in everything they tried to do after K10. They had to flush the entire R&D pipeline because of the Bulldozer fiasco.
http://www.anandtech.com/show/5058/amds-opteron-interlagos-6200/14AMD promised us (in 2009/2010) that the Opteron 6200 would be significantly faster than the 6100: "unprecedented server performance gains". That is somewhat the case if you recompile your software with the latest and greatest optimized compiler as AMD's own SPEC CINT (+19%), CFP 2006 (+11%) and Linpack benchmarks (+32%) show.
One of the real advantages of a new processor architecture (prime examples where the K7 and K8) is if it performs well in older software too, without requiring a recompile.
Hey, you detected my sarcasm. If you looked closely, I had both positive and negative points in this list. So the kind of effect of JF's work is up to you. I think the most likely thing is that we take such forums as too important as nearly noone among our engineers knows them (sometimes unfortunately, sometimes fortunately). And we're doing ADAS and more future stuff.LOL. Are you serious?
AMD's decline could be more attributed to him joining AMD, than leaving it.
He made an idiot out of himself on just about every computer forum, insisting Bulldozer wouldn't suffer IPC loss.
I
When did they flush the entire pipeline?
I have to admit, that I never bought one. So it was me, who caused the end of Bulldozer. Ok, I don't care. Oops, that was someone else. ^^he wanted to add "too late" to the sentence, but then his overclocked bulldozer crashed...
Sorry for formulating complex sentences. What you mean, falls underWhere are the Opterons Steamroller and Excavator?
But Steamroller and Excavator microarchitectures do exist. But given the situations surrounding their launches, would you give processors based on them a big chance to regain some share? Wouldn't that be nearly useless instead?Dresdenboy said:They left out finishing some projects like Krishna, Wichita, Skybridge, and others, which was either related to GF processes, market situations or changed plans.
Sorry for formulating complex sentences. What you mean, falls under
But Steamroller and Excavator microarchitectures do exist. But given the situations surrounding their launches, would you give processors based on them a big chance to regain some share? Wouldn't that be nearly useless instead?
We're talking µarchs and Carrizo here (a mobile part), and your context seems to be fixed on servers, to find some negative points. Are you an IT guy? I know ours, so.. to my last point.
Sorry friend that was rhetorical, I was trying to derail the server and bulldozer talk.
Do you have a link to that noise?
Mobile is nearly as bad, for both apus and dgpus. Will Carrizo change that? Perhaps, but I would not count on it.
Why are you being cynical? Or are you?Carrizo has already changed things in terms of hardware capabilities. It really is a good chip, as shown by the limited reviews we've seen to date. If they don't sell then so be it. The buying public votes with their wallets, and if they want hardware monoculture then we'll pretty much be stuck with it, the end.
As we basically are already told it is more efficient than the i5 5200u in various scenarios the only thing keeping AMD back is Intel's sleezy practices.
It could've been the other way round. They had the plan for another server processor from the beginning. That's as business is expected to happen if it is full of MBAs. The R&D teams and engineers have to deliver. But with such complex things as CPUs where you've still to find the solutions, which are already scheduled and tied to milestones, there could always be delays, buggy features, wrong assumptions (heuristics), imprecise simulations, etc. This is the human factor at work at every level.
They left out finishing some projects like Krishna, Wichita, Skybridge, and others, which was either related to GF processes, market situations or changed plans.
When did they flush the entire pipeline? They left out finishing some projects like Krishna, Wichita, Skybridge, and others, which was either related to GF processes, market situations or changed plans. The last big µarch thing being cancelled which I know of is David Christie's (and even Jim Keller's) original K8 design. Nothing is really missing in the construction line. Ok, the only thing I might miss from the original µarch roadmap is "greater parallelism" of SR, but this is interpretation (in the end +0.1% is "greater"). Other topics like ASF have been developed, but didn't get a go - possibly due to discontinueing the server line. Otherwise they'd have announced it, since ASF is nothing else than TSX.
Chuck Moore proposed throughput (more threads) being the solution. And he (or someone else) decided to take the risk of not getting enough compiler support and lower performance on existing code and code compiled for other archs. This is a decision and didn't play out. But that's economic life in a perfection seeking world. Nobody has a crystal ball. And only bigger companies have enough power to ensure the following of the software crowd.
The fact there are basically no quality AMD notebooks in the US market. Also contra revenue tactics.Could you tell us more about those "sleazy practices"? Thanks.
Waiting for more concrete info is a good idea. And blaming someone else that is abusing it's power and using that power to mistreat consumers due to lack of competition. Well I guess blaming some one else is totally justified in such a scenario and I will continue to do so. Until the underdog is not longer the underdog and we have actual fair competition.That Toms article was basically a rehash of AMD's PR slides. I will withhold judgement until we see some independent tests of shipping hardware. But hey all is good in AMD land. If the product fails, you can always blame someone else.